Cookies

We use cookies to ensure that we give you the best experience on our website. By continuing to browse this repository, you give consent for essential cookies to be used. You can read more about our Privacy and Cookie Policy.


Durham Research Online
You are in:

INTERACTION: A Generative XAI Framework for Natural Language Inference Explanations

Yu, Jialin and Cristea, Alexandra I. and Harit, Anoushka and Sun, Zhongtian and Aduragba, Olanrewaju Tahir and Shi, Lei and Al Moubayed, Noura (2022) 'INTERACTION: A Generative XAI Framework for Natural Language Inference Explanations.', The 2022 International Joint Conference on Neural Networks (IJCNN) Padova, Italy, 18-23 July 2022.

Abstract

XAI with natural language processing aims to produce human-readable explanations as evidence for AI decisionmaking, which addresses explainability and transparency. However, from an HCI perspective, the current approaches only focus on delivering a single explanation, which fails to account for the diversity of human thoughts and experiences in language. This paper thus addresses this gap, by proposing a generative XAI framework, INTERACTION (explaIn aNd predicT thEn queRy with contextuAl CondiTional varIational autO-eNcoder). Our novel framework presents explanation in two steps: (step one) Explanation and Label Prediction; and (step two) Diverse Evidence Generation. We conduct intensive experiments with the Transformer architecture on a benchmark dataset, e-SNLI [1]. Our method achieves competitive or better performance against state-of-the-art baseline models on explanation generation (up to 4.7% gain in BLEU) and prediction (up to 4.4% gain in accuracy) in step one

Item Type:Conference item (Paper)
Full text:(AM) Accepted Manuscript
Download PDF
(486Kb)
Status:Peer-reviewed
Publisher Web site:https://ieeexplore.ieee.org/xpl/conhome/1000500/all-proceedings
Publisher statement:© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Date accepted:26 April 2022
Date deposited:01 September 2022
Date of first online publication:2022
Date first made open access:01 September 2022

Save or Share this output

Export:
Export
Look up in GoogleScholar